Re: [PATCH] proc: show locks in /proc/pid/fdinfo/X

[Jeff Layton]

On Thu,  5 Mar 2015 18:37:18 +0300
Andrey Vagin <avagin@xxxxxxxxxx> wrote:

> Let's show locks which are associated with a file descriptor in
> its fdinfo file.
> 
> Currently we don't have a reliable way to determine who holds a lock.
> We can find some information in /proc/locks, but PID which is reported
> there can be wrong. For example, a process takes a lock, then forks a
> child and dies. In this case /proc/locks contains the parent pid, which
> can be reused by another process.
> 
> $ cat /proc/locks
> ...
> 6: FLOCK  ADVISORY  WRITE 324 00:13:13431 0 EOF
> ...
> 
> $ ps -C rpcbind
>   PID TTY          TIME CMD
>   332 ?        00:00:00 rpcbind
> 
> $ cat /proc/332/fdinfo/4
> pos:	0
> flags:	0100000
> mnt_id:	22
> lock:	1: FLOCK  ADVISORY  WRITE 324 00:13:13431 0 EOF
> 
> $ ls -l /proc/332/fd/4
> lr-x------ 1 root root 64 Mar  5 14:43 /proc/332/fd/4 -> /run/rpcbind.lock
> 
> $ ls -l /proc/324/fd/
> total 0
> lrwx------ 1 root root 64 Feb 27 14:50 0 -> /dev/pts/0
> lrwx------ 1 root root 64 Feb 27 14:50 1 -> /dev/pts/0
> lrwx------ 1 root root 64 Feb 27 14:49 2 -> /dev/pts/0
> 
> You can see that the process with the 324 pid doesn't hold the lock.
> 
> This information is required for proper dumping and restoring file
> locks.
> 
> Cc: Jonathan Corbet <corbet@xxxxxxx>
> Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
> Cc: Jeff Layton <jlayton@xxxxxxxxxxxxxxx>
> Cc: "J. Bruce Fields" <bfields@xxxxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxxx>
> Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
> Signed-off-by: Andrey Vagin <avagin@xxxxxxxxxx>
> ---
>  Documentation/filesystems/proc.txt |  4 ++++
>  fs/locks.c                         | 38 ++++++++++++++++++++++++++++++++++++++
>  fs/proc/fd.c                       | 27 ++++++++++++++++++---------
>  include/linux/fs.h                 |  7 +++++++
>  4 files changed, 67 insertions(+), 9 deletions(-)
> 
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index a07ba61..6331623 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -1704,6 +1704,10 @@ A typical output is
>  	flags:	0100002
>  	mnt_id:	19
>  
> +All locks associated with a file descriptor are shown in its fdinfo too.
> +
> +lock:       1: FLOCK  ADVISORY  WRITE 359 00:13:11691 0 EOF
> +
>  The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
>  pair provide additional information particular to the objects they represent.
>  
> diff --git a/fs/locks.c b/fs/locks.c
> index 365c82e..815f832 100644
> --- a/fs/locks.c
> +++ b/fs/locks.c
> @@ -2592,6 +2592,44 @@ static int locks_show(struct seq_file *f, void *v)
>  	return 0;
>  }
>  
> +static void __show_fd_locks(struct seq_file *f,
> +			struct list_head *head, int *id,
> +			struct file *filp, struct files_struct *files)
> +{
> +	struct file_lock *fl;
> +
> +	list_for_each_entry(fl, head, fl_list) {
> +
> +		if (filp != fl->fl_file)
> +			continue;
> +		if (fl->fl_owner != files &&
> +		    fl->fl_owner != filp)
> +			continue;
> +
> +		(*id)++;
> +		seq_puts(f, "lock:\t");
> +		lock_get_status(f, fl, *id, "");
> +	}
> +}
> +
> +void show_fd_locks(struct seq_file *f,
> +		  struct file *filp, struct files_struct *files)
> +{
> +	struct inode *inode = file_inode(filp);
> +	struct file_lock_context *ctx;
> +	int id = 0;
> +
> +	ctx = inode->i_flctx;
> +	if (!ctx)
> +		return;
> +
> +	spin_lock(&ctx->flc_lock);
> +	__show_fd_locks(f, &ctx->flc_flock, &id, filp, files);
> +	__show_fd_locks(f, &ctx->flc_posix, &id, filp, files);
> +	__show_fd_locks(f, &ctx->flc_lease, &id, filp, files);
> +	spin_unlock(&ctx->flc_lock);
> +}
> +
>  static void *locks_start(struct seq_file *f, loff_t *pos)
>  	__acquires(&blocked_lock_lock)
>  {
> diff --git a/fs/proc/fd.c b/fs/proc/fd.c
> index 8e5ad83..f04e13d 100644
> --- a/fs/proc/fd.c
> +++ b/fs/proc/fd.c
> @@ -8,6 +8,7 @@
>  #include <linux/security.h>
>  #include <linux/file.h>
>  #include <linux/seq_file.h>
> +#include <linux/fs.h>
>  
>  #include <linux/proc_fs.h>
>  
> @@ -48,16 +49,24 @@ static int seq_show(struct seq_file *m, void *v)
>  		put_files_struct(files);
>  	}
>  
> -	if (!ret) {
> -		seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n",
> -			   (long long)file->f_pos, f_flags,
> -			   real_mount(file->f_path.mnt)->mnt_id);
> -		if (file->f_op->show_fdinfo)
> -			file->f_op->show_fdinfo(m, file);
> -		ret = seq_has_overflowed(m);
> -		fput(file);
> -	}
> +	if (ret)
> +		return ret;
> +
> +	seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n",
> +		   (long long)file->f_pos, f_flags,
> +		   real_mount(file->f_path.mnt)->mnt_id);
> +
> +	show_fd_locks(m, file, files);
> +	ret = seq_has_overflowed(m);
> +	if (ret)
> +		goto out;
> +
> +	if (file->f_op->show_fdinfo)
> +		file->f_op->show_fdinfo(m, file);
> +	ret = seq_has_overflowed(m);
>  
> +out:
> +	fput(file);
>  	return ret;
>  }
>  
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index b4d71b5..ba0bd2a 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1018,6 +1018,9 @@ extern void lease_get_mtime(struct inode *, struct timespec *time);
>  extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
>  extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
>  extern int lease_modify(struct file_lock *, int, struct list_head *);
> +struct files_struct;
> +extern void show_fd_locks(struct seq_file *f,
> +			 struct file *filp, struct files_struct *files);
>  #else /* !CONFIG_FILE_LOCKING */
>  static inline int fcntl_getlk(struct file *file, unsigned int cmd,
>  			      struct flock __user *user)
> @@ -1154,6 +1157,10 @@ static inline int lease_modify(struct file_lock *fl, int arg,
>  {
>  	return -EINVAL;
>  }
> +
> +struct files_struct;
> +static inline void show_fd_locks(struct seq_file *f,
> +			struct file *filp, struct files_struct *files) {}
>  #endif /* !CONFIG_FILE_LOCKING */
>  
>  

Looks reasonably sane to me. Via what tree should this go in?

Acked-by: Jeff Layton <jlayton@xxxxxxxxxxxxxxx>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/